Python使用scrapy抓取网站sitemap信息 Python使用scrapy抓取网站sitemap信息的方法

import re
from scrapy.spider import BaseSpider
from scrapy import log
from scrapy.utils.response import body_or_str
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector
class SitemapSpider(BaseSpider):
 name = "SitemapSpider"
 start_urls = ["http://www.domain.com/sitemap.xml"]
 def parse(self, response):
  nodename = 'loc'
  text = body_or_str(response)
  r = re.compile(r"(<%s[\s>])(.*?)(</%s>)"%(nodename,nodename),re.DOTALL)
  for match in r.finditer(text):
   url = match.group(2)
   yield Request(url, callback=self.parse_page)
 def parse_page(self, response):
    hxs = HtmlXPathSelector(response)
    #Mock Item
  blah = Item()
  #Do all your page parsing and selecting the elemtents you want
    blash.divText = hxs.select('//div/text()').extract()[0]
  yield blah